Open AccessCloud based Resource Scheduling Methodology for Data-Intensive Smart Cities and Industrial Applications
Author(s) -
S. Ma,
Jichang Chen,
Yang Zhang,
Anand Shrivastava,
Hari Mohan
Publication year - 2021
Publication title -
scalable computing. practice and experience
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.192
H-Index - 18
ISSN - 1895-1767
DOI - 10.12694/scpe.v22i2.1899
Subject(s) - computer science , cloud computing , particle swarm optimization , software deployment , ant colony optimization algorithms , big data , scheduling (production processes) , distributed computing , operations research , data mining , engineering , artificial intelligence , algorithm , operations management , operating system
For the data-intensive applications, resource planning and scheduling has become an important part for smart cities. The cloud computing techniques are being used for planning and scheduling of resources in data-intensive applications. The regular methodologies being used are adequately successful for giving the asset allotment yet they do not provide time effectiveness during task execution. This article presents an effective and time prioritization based smart resource management platform employing the Cuckoo Search based Optimized Resource Allocation (CSO-RA) methodology. The opensource JStorm platform is utilized for dynamic asset planning while using big data analytics and the outcomes of the experimentation are observed using various assessment parameters. The proposed (CSO-RA) system is compared with the current methodologies like particle swarm optimization (PSO), ant colony optimization (ACO) and genetic algorithm (GA) based optimization methodologies and the viability of the proposed framework is established. The percentage of optimality observed for CSO-RA algorithm is 97\% and overall resource deployment rate of 28\% is achieved using CSO-RA method which is comparatively much better than PSO, GA and ACO conventional algorithms. Feasible outcomes are obtained by using the CSO-RA methodology for cloud computing based large scale optimization-based data intensive industrial applications.